Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions of approval and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ">.
    -0.52
    ModelSerializer
    -0.45
     theirs
    -0.45
    bigcap
    -0.44
    っこう
    -0.44
    engagent
    -0.44
    ాయి
    -0.43
     He
    -0.43
    mended
    -0.43
    Tē
    -0.43
    POSITIVE LOGITS
    adaptiveStyles
    0.67
    出版年
    0.65
     anyone
    0.65
     users
    0.62
     everyone
    0.62
     vegetarians
    0.62
     autorytatywna
    0.62
     usuarios
    0.60
    openzeppelin
    0.60
     newOwner
    0.59
    Act Density 0.269%

    No Known Activations